Systems, Man, and Cybernetics

 

Home

• [P612] Associative Memories with Multi-Valued Cellular Neural Networks and Its Application to Disease Diagnosis
  Author(s): Takuma Akiduki, Zhong Zhang
  
  

  Abstract
  Cellular neural networks (CNNs) are one type of interconnected neural networks and differ from the well-known Hopfield model in that each cell has a piecewise linear output characteristic. In this paper, we present a multi-valued CNN model that each nonlinear element consist of a multi-valued output function. The function is defined by a linear combination of the piecewise linear functions. And we conduct computer experiments of auto-associative recall to verify characteristic as an associative memory with our multi-valued CNN. In addition, we also apply our multi-valued CNN to diagnosis disease problem. Results obtained show that multi-valued CNN improve classification accuracy by selecting output level $q$ properly. Moreover, these results also show that multi-valued associative memory can expand both flexibility of designing memory pattern and applicability.

  
   

Full Text (PDF)